Follow the instructions posted at https://ds202-at-isu.github.io/labs.html for the lab assignment. The work is meant to be finished during the lab time, but you have time until Monday evening to polish things.
Include your answers in this document (Rmd file). Make sure that it knits properly (into the md file). Upload both the Rmd and the md file to your repository.
All submissions to the github repo will be automatically uploaded for grading once the due date is passed. Submit a link to your repository on Canvas (only one submission per team) to signal to the instructors that you are done with your submission.
Extract from the data below two data sets in long form
deaths and returns
av <- read.csv("https://raw.githubusercontent.com/fivethirtyeight/data/master/avengers/avengers.csv", stringsAsFactors = FALSE)
head(av)## URL
## 1 http://marvel.wikia.com/Henry_Pym_(Earth-616)
## 2 http://marvel.wikia.com/Janet_van_Dyne_(Earth-616)
## 3 http://marvel.wikia.com/Anthony_Stark_(Earth-616)
## 4 http://marvel.wikia.com/Robert_Bruce_Banner_(Earth-616)
## 5 http://marvel.wikia.com/Thor_Odinson_(Earth-616)
## 6 http://marvel.wikia.com/Richard_Jones_(Earth-616)
## Name.Alias Appearances Current. Gender Probationary.Introl
## 1 Henry Jonathan "Hank" Pym 1269 YES MALE
## 2 Janet van Dyne 1165 YES FEMALE
## 3 Anthony Edward "Tony" Stark 3068 YES MALE
## 4 Robert Bruce Banner 2089 YES MALE
## 5 Thor Odinson 2402 YES MALE
## 6 Richard Milhouse Jones 612 YES MALE
## Full.Reserve.Avengers.Intro Year Years.since.joining Honorary Death1 Return1
## 1 Sep-63 1963 52 Full YES NO
## 2 Sep-63 1963 52 Full YES YES
## 3 Sep-63 1963 52 Full YES YES
## 4 Sep-63 1963 52 Full YES YES
## 5 Sep-63 1963 52 Full YES YES
## 6 Sep-63 1963 52 Honorary NO
## Death2 Return2 Death3 Return3 Death4 Return4 Death5 Return5
## 1
## 2
## 3
## 4
## 5 YES NO
## 6
## Notes
## 1 Merged with Ultron in Rage of Ultron Vol. 1. A funeral was held.
## 2 Dies in Secret Invasion V1:I8. Actually was sent tto Microverse later recovered
## 3 Death: "Later while under the influence of Immortus Stark committed a number of horrible acts and was killed.' This set up young Tony. Franklin Richards later brought him back
## 4 Dies in Ghosts of the Future arc. However "he had actually used a hidden Pantheon base to survive"
## 5 Dies in Fear Itself brought back because that's kind of the whole point. Second death in Time Runs Out has not yet returned
## 6 <NA>Get the data into a format where the five columns for Death[1-5] are
replaced by two columns: Time, and Death. Time should be a number
between 1 and 5 (look into the function parse_number);
Death is a categorical variables with values “yes”, “no” and ““. Call
the resulting data set deaths.
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondeaths <- av |>
pivot_longer(cols = c("Death1", "Death2", "Death3", "Death4", "Death5"),
names_to = "Time",
values_to = "Death") |>
filter(Death != "")
deaths$Time <- parse_number(deaths$Time)
head(deaths)## # A tibble: 6 × 18
## URL Name.Alias Appearances Current. Gender Probationary.Introl
## <chr> <chr> <int> <chr> <chr> <chr>
## 1 http://marvel.wiki… "Henry Jo… 1269 YES MALE ""
## 2 http://marvel.wiki… "Janet va… 1165 YES FEMALE ""
## 3 http://marvel.wiki… "Anthony … 3068 YES MALE ""
## 4 http://marvel.wiki… "Robert B… 2089 YES MALE ""
## 5 http://marvel.wiki… "Thor Odi… 2402 YES MALE ""
## 6 http://marvel.wiki… "Thor Odi… 2402 YES MALE ""
## # ℹ 12 more variables: Full.Reserve.Avengers.Intro <chr>, Year <int>,
## # Years.since.joining <int>, Honorary <chr>, Return1 <chr>, Return2 <chr>,
## # Return3 <chr>, Return4 <chr>, Return5 <chr>, Notes <chr>, Time <dbl>,
## # Death <chr>Similarly, deal with the returns of characters.
returns <- av |>
pivot_longer(cols = c("Return1", "Return2", "Return3", "Return4", "Return5"),
names_to = "Time",
values_to = "Return") |>
filter(Return != "")
returns$Time <- parse_number(returns$Time)
head(returns)## # A tibble: 6 × 18
## URL Name.Alias Appearances Current. Gender Probationary.Introl
## <chr> <chr> <int> <chr> <chr> <chr>
## 1 http://marvel.wiki… "Henry Jo… 1269 YES MALE ""
## 2 http://marvel.wiki… "Janet va… 1165 YES FEMALE ""
## 3 http://marvel.wiki… "Anthony … 3068 YES MALE ""
## 4 http://marvel.wiki… "Robert B… 2089 YES MALE ""
## 5 http://marvel.wiki… "Thor Odi… 2402 YES MALE ""
## 6 http://marvel.wiki… "Thor Odi… 2402 YES MALE ""
## # ℹ 12 more variables: Full.Reserve.Avengers.Intro <chr>, Year <int>,
## # Years.since.joining <int>, Honorary <chr>, Death1 <chr>, Death2 <chr>,
## # Death3 <chr>, Death4 <chr>, Death5 <chr>, Notes <chr>, Time <dbl>,
## # Return <chr>Based on these datasets calculate the average number of deaths an Avenger suffers.
For each team member, copy this part of the report.
Each team member picks one of the statements in the FiveThirtyEight analysis and fact checks it based on the data. Use dplyr functionality whenever possible.
“Out of 173 listed Avengers, how many have died at least once after joining the team?”
# Count Avengers who died at least once
dead_avengers <- deaths |>
filter(Death == "YES") |>
distinct(Name.Alias)
num_dead <- nrow(dead_avengers)
# Total number of Avengers
total_avengers <- nrow(av)
# Percentage
percent_dead <- (num_dead / total_avengers) * 100
num_dead## [1] 64## [1] 173## [1] 36.99422After filtering the deaths data set for Avengers whose death status was marked “YES” and removing duplicates, there are 64 unique Avengers who died at least once. Since the data set contains 173 total Avengers, approximately 36.9% of Avengers experienced at least one death, which matches the article’s claim that about 40% of Avengers have died (or at least, it’s close enough).
Upload your changes to the repository. Discuss and refine answers as a team.